joseph.ergo@proton.me | Portfolio | Resume PDF | Linked-In | +212 713-617-633

Available immediately for full/part-time remote roles

GFT GROUP

Show the code

## SETUP
from pathlib import Path
import duckdb
from tqdm.notebook import tqdm
import datetime
import copy
import polars as pl
import plotly.express as px
import plotly.io as pio
import re
from concurrent.futures import ThreadPoolExecutor
import plotly.graph_objects as go
import networkx as nx
import numpy as np
# pio.renderers.default = 'plotly_mimetype'
pio.renderers.default = 'jupyterlab+notebook'
pio.templates.default = "plotly_white"

path_data = Path.cwd()/'data'/'03_rdb'
path_data_companies = path_data/'companies_table.parquet'
path_data_experience = path_data/'experience_table.parquet'
path_data_emails = path_data/'emails_table.parquet'
path_data_education = path_data/'education_table.parquet'
path_data_school = path_data/'school_table.parquet'
path_data_persona = path_data/'persona_table.parquet'
path_data_profiles = path_data/'profiles_table.parquet'

path_output_images = Path.cwd()/'output'/'images'

conn = duckdb.connect()

conn.execute("SET temp_directory = 'temp';")
conn.execute("SET memory_limit = '10GB';")
conn.execute("SET max_temp_directory_size = '100GB';")
conn.execute("SET threads = 8;")
conn.execute("SET preserve_insertion_order = false;")
conn.execute("SET enable_progress_bar = true;")
conn.execute("SET enable_progress_bar_print = true;")

Show the code

df = pl.read_parquet('03_target_companies3.parquet')
df_yearly_new_hires_per_indestry = pl.read_parquet('03_yearly_new_hires_per_indestry.parquet')

Show the code

current_company_id = "&-friends"
current_company_id = pl.read_json("04__control__.json")[0,'current_company_id']
query = f"""
SELECT *
FROM read_parquet('{path_data_companies}')
WHERE company_id = '{current_company_id}'
"""
df_company_by_company_id = pl.DataFrame(conn.execute(query).df())

current_company_name = df_company_by_company_id[0,'company_name']
current_company_indestry = df_company_by_company_id[0,'company_industry']

current_company_parquet = Path.cwd()/'output'/'company_data'/f"{current_company_id}.parquet"

Show the code

# Info about personas status from company_id

Show the code

query = f"""
SELECT *
FROM read_parquet('{path_data_experience}')
WHERE company_id = '{current_company_id}'
"""
df_experiences_by_company_id = pl.DataFrame(conn.execute(query).df())

Show the code

personas_whitout_end_date = df_experiences_by_company_id.filter(pl.col('end_date').is_null())
personas_who_got_raise = df_experiences_by_company_id.filter((pl.col('end_date').is_not_null()) &
                                     pl.col('persona_id').is_in(personas_whitout_end_date['persona_id'].to_list()))
personas_who_stayed = (pl
                      .concat([personas_whitout_end_date, personas_who_got_raise])
                      .sort('start_date')
                      .group_by('persona_id')
                      .agg(
                          pl.col('title_name').last(),
                          pl.col('is_primary').last(),
                          pl.col('start_date').min(),
                          pl.col('end_date').max(),
                          pl.col('title_name').count().alias('changes'),
                          pl.col('title_name').unique().alias('all_title_name'),
                      )
                      .with_columns(
                          pl.lit(True).alias('still_associated'),
                          pl.lit(None).alias('end_date')
                      )
                      .sort('changes')
                             )

Show the code

personas_who_left = df_experiences_by_company_id.filter((pl.col('end_date').is_not_null()) & ~pl.col('persona_id').is_in(personas_who_stayed['persona_id'].to_list()) )
personas_who_left = (personas_who_left
                     .sort('start_date')
                     .group_by('persona_id')
                     .agg(
                          pl.col('title_name').last(),
                          pl.col('is_primary').last(),
                          pl.col('start_date').min(),
                          pl.col('end_date').max(),
                          pl.col('title_name').count().alias('changes'),
                          pl.col('title_name').unique().alias('all_title_name'),
                              )
                     .with_columns(
                         pl.lit(False).alias('still_associated'),
                         
                     )
                     .sort('changes'))

Show the code

df_personas_who_worked_in_company = pl.concat([personas_who_stayed, personas_who_left], how='vertical_relaxed').with_columns(
    (pl.col('end_date').dt.year()-pl.col('start_date').dt.year()).alias('work_durration')
).sort('work_durration')

Show the code

import dns.resolver
import smtplib
import socket

def check_deliverability(email_address):
    """
    Checks the deliverability of an email address by verifying MX records
    and performing an SMTP connection test.
    """
    if '@' not in email_address:
        return False
    
    domain = email_address.split('@')[1]
    
    # Check for MX records
    try:
        mx_records = dns.resolver.resolve(domain, 'MX')
        if not mx_records:
            return False
    except (dns.resolver.NoAnswer, dns.resolver.NXDOMAIN, dns.resolver.Timeout):
        return False

    # Perform SMTP connection test
    mx_host = str(mx_records[0].exchange)
    
    # Validate MX hostname before attempting connection
    try:
        # Test if hostname can be properly encoded
        mx_host.encode('idna')
    except UnicodeError:
        return False
    
    try:
        with smtplib.SMTP(mx_host, timeout=10) as smtp:
            smtp.set_debuglevel(0)
            smtp.helo(socket.gethostname())
            smtp.mail('test@example.com')
            code, _ = smtp.rcpt(email_address)

            return code == 250  # 250 indicates valid email address
            
    except (smtplib.SMTPException, socket.error, UnicodeError):
        return False

Show the code

# info of all personas info
list_w = []
for word in df_experiences_by_company_id['persona_id'].unique().to_list():
    list_w.append(f"'{word}'")
list_for_in = ', '.join(list_w)

query = f"""
SELECT *
FROM read_parquet('{path_data_persona}')
WHERE persona_id IN ({list_for_in})
"""
df_all_personas = pl.DataFrame(conn.execute(query).df())

# info of all personas profiles
list_w = []
for word in df_experiences_by_company_id['persona_id'].unique().to_list():
    list_w.append(f"'{word}'")
list_for_in = ', '.join(list_w)

query = f"""
SELECT *
FROM read_parquet('{path_data_profiles}')
WHERE persona_id IN ({list_for_in})
"""
df_all_personas_profile = pl.DataFrame(conn.execute(query).df())
df_all_personas_profile_f = df_all_personas_profile.group_by('persona_id').agg(pl.col('url').unique())

# info of all personas email
list_w = []
for word in df_experiences_by_company_id['persona_id'].unique().to_list():
    list_w.append(f"'{word}'")
list_for_in = ', '.join(list_w)

query = f"""
SELECT *
FROM read_parquet('{path_data_emails}')
WHERE persona_id IN ({list_for_in}) AND type == 'personal'
"""
df_all_personas_emails = pl.DataFrame(conn.execute(query).df())

def def_polars_fix_gmail(x):
    if "@gmail" in x:
        first_part = x.split('@')[0]
        second_part = x.split('@')[1]
        return f"{first_part.replace(".",'')}@{second_part}"
    else:
        return x

df_all_personas_emails_f = (df_all_personas_emails
                            .with_columns(pl.col('address')
                                          .map_elements(def_polars_fix_gmail, return_dtype=pl.String)
                                          .alias('normalised_emails'))
                            .unique('normalised_emails', keep='first')
                            .sort('persona_id')
                            .drop('normalised_emails')
                         )
df_all_personas_emails_f = (df_all_personas_emails_f.group_by('persona_id').agg(pl.col('address').unique(),pl.col('type').unique()))
df_all_personas_plus = df_all_personas.join(df_all_personas_emails_f, on='persona_id', how='left')

df_full_personas_who_worked_in_company = (df_personas_who_worked_in_company
                                       .join(df_all_personas_plus, on='persona_id', how='left')
                                       .join(df_all_personas_profile_f, on='persona_id', how='left')
                                      )

df_full_personas_who_worked_in_company = (
    df_full_personas_who_worked_in_company.with_columns(
        (pl.col("start_date").fill_null(pl.col("start_date").min()))
        .dt.year()
        .alias("start_year"),
        (pl.col("end_date").dt.year()).alias("end_year"),
    )
)

work_years = []
for i in range(len(df_full_personas_who_worked_in_company)):
    start_y = df_full_personas_who_worked_in_company[i, "start_year"]
    if df_full_personas_who_worked_in_company[i, "end_year"]:
        end_y = df_full_personas_who_worked_in_company[i, "end_year"]
    else:
        end_y = 2020

    tmp_work_years = []
    for y in range(start_y, end_y + 1):
        tmp_work_years.append(y)

    work_years.append(tmp_work_years)

df_full_personas_who_worked_in_company = (
    df_full_personas_who_worked_in_company.with_columns(
        pl.Series("work_years", work_years)
    )
)

# add hireups
title_name_match = ["ceo","chief","founder","owner","president","vp","vice","director",
    "cfo","cto","partner","head of","hr ","human","talent","senior","manager","lead"]

df_full_personas_who_worked_in_company = (df_full_personas_who_worked_in_company
    .with_columns(
        pl.when(pl.col('title_name').str.contains_any(title_name_match)).then(True).otherwise(False).alias("higher_up")
    ))



df_tmp_email_checker = (
    df_full_personas_who_worked_in_company
    .filter(
            pl.col('still_associated')==True,
            pl.col('address').list.len()>0
    )
        ['persona_id','address']
        .explode('address')
)

# if current_company_parquet.exists():
#     df_pre_full_personas_who_worked_in_company = pl.read_parquet(current_company_parquet)
#     list_pre_deliverable_address = df_pre_full_personas_who_worked_in_company['address'].drop_nulls().explode().to_list()
# else:
#     list_pre_deliverable_address = []

# list_of_emails_to_check = df_tmp_email_checker['address'].drop_nulls().to_list()
# list_lists_email_check = []

# var_total_emails = len(list_of_emails_to_check)
# var_current_email_count = 0

# def def_check_and_populate(email_to_check):
#     global list_lists_email_check, var_current_email_count
#     if email_to_check in list_pre_deliverable_address:
#         list_lists_email_check.append([email_to_check, True])
#     elif '@gmail' in email_to_check:
#         list_lists_email_check.append([email_to_check, True])
#     else:
#         try:
#             is_deliverable = check_deliverability(email_to_check)
#             list_lists_email_check.append([email_to_check, is_deliverable])
#         except:
#             list_lists_email_check.append([email_to_check, False])
#     var_current_email_count += 1
#     print(' '*10, end='\r')
#     print(round(var_current_email_count/var_total_emails,5), end='\r')

# with ThreadPoolExecutor(max_workers=20) as executor:
#     results = list(executor.map(def_check_and_populate, list_of_emails_to_check))

# df_email_check = pl.DataFrame(list_lists_email_check, schema=["address", "deliverable"], orient="row")
# try:
#     df_tmp_email_checker_f = (
#         df_tmp_email_checker
#             .join(df_email_check, on='address')
#             .filter(pl.col('deliverable')==True)
#             .group_by('persona_id').agg(pl.col('address').unique().alias("deliverable_address"))
#     )
# except:
#     df_tmp_email_checker_f = pl.DataFrame()

# if df_tmp_email_checker_f.is_empty():
#     df_full_personas_who_worked_in_company = df_full_personas_who_worked_in_company.join(df_tmp_email_checker.rename({'address':'deliverable_address'}), on="persona_id", how='left')
# else:
#     df_full_personas_who_worked_in_company = df_full_personas_who_worked_in_company.join(df_tmp_email_checker_f, on="persona_id", how='left')

Show the code

# Info about personas experiences

Show the code

# info of all experiences[]
list_w = []
for word in df_experiences_by_company_id['persona_id'].unique().to_list():
    list_w.append(f"'{word}'")

list_for_in = ', '.join(list_w)
query = f"""
SELECT *
FROM read_parquet('{path_data_experience}')
WHERE persona_id IN ({list_for_in})
"""
df_all_personas_experiences = pl.DataFrame(conn.execute(query).df())


# info of all comapnies in said experiences
list_w = []
for word in df_all_personas_experiences['company_id'].unique().to_list():
    if "'" not in word:
        list_w.append(f"'{word}'")

list_for_in = ', '.join(list_w)
query = f"""
SELECT company_id, company_name, company_industry, company_linkedin_url, company_location_country
FROM read_parquet('{path_data_companies}')
WHERE company_id IN ({list_for_in})
"""
df_all_companies = pl.DataFrame(conn.execute(query).df())

df_full_personas_experiences_plus = df_all_personas_experiences.join(df_all_companies, on='company_id', how='left')

df_full_personas_experiences_plus = (
    df_full_personas_experiences_plus
    .with_columns(
        pl.when(
            pl.col('company_id')==current_company_id
        )
        .then(True)
        .otherwise(False)
        .alias('target')
    )
)

Show the code

# Info about personas education

Show the code

# info of all experiences
list_w = []
for word in df_experiences_by_company_id['persona_id'].unique().to_list():
    list_w.append(f"'{word}'")

list_for_in = ', '.join(list_w)
query = f"""
SELECT *
FROM read_parquet('{path_data_education}')
WHERE persona_id IN ({list_for_in})
"""
df_all_personas_education = pl.DataFrame(conn.execute(query).df())


#ifon of allcomapnies in said experiences
list_w = []
for word in df_all_personas_education['school_id'].unique().to_list():
    if "'" not in word:
        list_w.append(f"'{word}'")

if list_w:
    list_for_in = ', '.join(list_w)
    query = f"""
    SELECT school_id, school_name, school_type, school_website, school_location_country
    FROM read_parquet('{path_data_school}')
    WHERE school_id IN ({list_for_in})
    """
    df_all_school = pl.DataFrame(conn.execute(query).df())
    
    df_full_personas_education_plus = df_all_personas_education.join(df_all_school, on='school_id', how='left')
else:
    df_full_personas_education_plus = df_all_personas_education

1 About the project

The project came to life after realizing that web scraping doesn’t allow deep-level filtering—without consuming too much time.The irony is, this project itself took me about a month, but the final RDB contains more data than I could ever scrape.

The raw data was 1.4 TB in size and holds information previously scraped.
Processing was done on my local machine using Python, Polars, and DuckDB, following this workflow:
- Processed raw data into structured Parquet files using Polars.
- Transformed each Parquet file into mini RDBs using Polars.
- Merged all mini RDBs into one using DuckDB.
- Analyzed and filtered data to fit the current project.

Alt text

2 EDA

2.1 information technology and services indestry’s yearly new recruit count

Show the code

list_of_unique_company_experience_years = []
for y in df_full_personas_who_worked_in_company['start_year'].unique().drop_nulls().to_list():
    if y not in list_of_unique_company_experience_years:
        list_of_unique_company_experience_years.append(y)
for y in df_full_personas_who_worked_in_company['end_year'].unique().drop_nulls().to_list():
    if y not in list_of_unique_company_experience_years:
        list_of_unique_company_experience_years.append(y)

list_year = []
list_state = []
list_count = []
list_names = []

def def_get_names_breked(tmp):
    if tmp.is_empty():
        names_string = ''
    else:
        tmp_list_name = []
        names_limit = 3
        row_limit = names_limit * 6
        for i, name in enumerate(tmp['full_name'].to_list()):
            ii = i+1
            tmp_list_name.append(name.title())
            if ii!=0 and ii%names_limit==0:
                tmp_list_name.append("<br>")
            if ii==row_limit:
                tmp_list_name.append("...")
                break
        names_string = ', '.join(tmp_list_name).replace(", <br>, ","<br>")
    return names_string

for y in list_of_unique_company_experience_years:
    #recuite state
    list_year.append(y)
    list_state.append('Recruited')
    tmp = df_full_personas_who_worked_in_company.filter(pl.col('start_year')==y).sort('full_name')
    list_count.append(len(tmp))
    list_names.append(def_get_names_breked(tmp))
    
    #recuite state
    list_year.append(y)
    list_state.append('Resigned')
    tmp = df_full_personas_who_worked_in_company.filter(pl.col('end_year')==y).sort('full_name')
    list_count.append(len(tmp))
    list_names.append(def_get_names_breked(tmp))

df_m_recruite_vs_resign = pl.DataFrame({
    'year':list_year,
    'status':list_state,
    'count':list_count,
    'names':list_names,})

2.2 gft group’s workforce status over the years

3 Persona company network graph

Show the code

gr_net = df_full_personas_experiences_plus.with_columns(pl.col('company_id').str.to_uppercase()).group_by('persona_id','company_id').agg(pl.len().alias('count')).sort('count')
list_top_in_network = gr_net['company_id'].value_counts().sort('count', descending=True)['company_id'].to_list()[:5]
gr_net_f = gr_net.filter(pl.col('company_id').is_in(list_top_in_network))

list_letters = ['A','B','C','D','E','F','G','H']
dict_company = {}
dict_company_rev = {}
for company, letter in zip(list_top_in_network, list_letters ):
    dict_company[letter] = company
    dict_company_rev[company] = letter

gr_gr_net_f = gr_net_f.sort('company_id').group_by('persona_id').agg(pl.col('company_id').unique().sort(),)

gr_gr_net_f2 = (
    gr_gr_net_f['company_id']
    .value_counts()
    .with_columns(
        # pl.col('company_id').list.join(', '),
        (pl.col('count')/len(gr_gr_net_f)).alias('per')
    )
    .sort('per',descending=True)
)

list_prob = []
for i in range(len(gr_gr_net_f2)):
    tmp_prob_letters = []
    for k in dict_company.keys():
        if dict_company[k] in gr_gr_net_f2[i]['company_id'][0].to_list():
            tmp_prob_letters.append(f' {k}')
        else:
            tmp_prob_letters.append(f'¬{k}')

    list_prob.append(f"P({' ∩ '.join(tmp_prob_letters)}) = {round(gr_gr_net_f2[i]['per'][0],4)}")
annon_prob_text = "<b>Probability Distribution:</b><br>" + '<br>'.join(list_prob)



# Create network graph
G = nx.Graph()
for persona, company in gr_net_f.select(['persona_id', 'company_id']).iter_rows():
    G.add_edge(persona, company)

# Get unique values
persona_ids = gr_net_f['persona_id'].unique().to_list()
company_ids = gr_net_f['company_id'].unique().to_list()

# Calculate degrees (connection counts)
degree_dict = dict(G.degree())

# Get min and max degrees for scaling
company_degrees = [degree_dict[c] for c in company_ids]
persona_degrees = [degree_dict[p] for p in persona_ids]

min_company_degree = min(company_degrees) if company_degrees else 1
max_company_degree = max(company_degrees) if company_degrees else 1
min_persona_degree = min(persona_degrees) if persona_degrees else 1
max_persona_degree = max(persona_degrees) if persona_degrees else 1

# Define size ranges
COMPANY_MIN_SIZE = 25
COMPANY_MAX_SIZE = 100
PERSONA_MIN_SIZE = 5
PERSONA_MAX_SIZE = 20

# print(f"Company connections range: {min_company_degree} - {max_company_degree}")
# print(f"Persona connections range: {min_persona_degree} - {max_persona_degree}")

# Sort companies by degree (size) in descending order
company_ids_sorted = sorted(company_ids, key=lambda x: degree_dict[x], reverse=True)

# Check if "Nokia" exists in the data
HIGHLIGHTED_COMPANY = current_company_id
HIGHLIGHTED_COMPANY_EXISTS = HIGHLIGHTED_COMPANY.lower() in [str(c).lower() for c in company_ids]

if HIGHLIGHTED_COMPANY_EXISTS:
    # Get the actual case-sensitive name
    highlighted_company = next(c for c in company_ids if str(c).lower() == HIGHLIGHTED_COMPANY.lower())
    # print(f"Highlighting company: {highlighted_company} (with {degree_dict[highlighted_company]} connections)")
else:
    # print(f"Warning: '{HIGHLIGHTED_COMPANY}' not found in company list")
    highlighted_company = None

# Create layout (companies on outer circle, ordered by size)
pos = {}
num_companies = len(company_ids_sorted)
radius_outer = 2.0

# Position companies on circle, ordered by size (largest first)
for i, company in enumerate(company_ids_sorted):
    # Start at top (90° or π/2 radians) and go counter-clockwise (add angle)
    # Counter-clockwise rotation: angle = start_angle + (i * 2π / num_companies)
    # This puts largest at top, next on left, then bottom, then right
    start_angle = np.pi / 2  # 90° at top
    
    # For counter-clockwise rotation
    angle = start_angle - (2 * np.pi * i / num_companies)
    
    # Convert to x, y coordinates
    pos[company] = (radius_outer * np.cos(angle), radius_outer * np.sin(angle))

# Position personas
for i, persona in enumerate(persona_ids):
    connected_companies = [c for c in company_ids if G.has_edge(persona, c)]
    if connected_companies:
        avg_x = np.mean([pos[c][0] for c in connected_companies])
        avg_y = np.mean([pos[c][1] for c in connected_companies])
        # Add jitter to spread out personas
        jitter_x = np.random.uniform(-0.2, 0.2)
        jitter_y = np.random.uniform(-0.2, 0.2)
        pos[persona] = (avg_x * 0.5 + jitter_x, avg_y * 0.5 + jitter_y)
    else:
        pos[persona] = (0, 0)

# Prepare edge traces
edge_x, edge_y = [], []
for edge in G.edges():
    x0, y0 = pos[edge[0]]
    x1, y1 = pos[edge[1]]
    edge_x.extend([x0, x1, None])
    edge_y.extend([y0, y1, None])

edge_trace = go.Scatter(
    x=edge_x, y=edge_y,
    line=dict(width=0.6, color='rgba(120, 120, 120, 0.15)'),
    hoverinfo='none',
    mode='lines')

# Prepare node traces with proportional sizing
company_x, company_y, company_text = [], [], []
company_color, company_size, company_hover = [], [], []
company_border_width = []  # For border thickness
company_border_color = []  # For border color

persona_x, persona_y = [], []
persona_color, persona_size, persona_hover = [], [], []

# Helper function to scale size proportionally
def scale_size(value, min_val, max_val, min_size, max_size):
    if max_val == min_val:
        return (min_size + max_size) / 2
    return min_size + (value - min_val) / (max_val - min_val) * (max_size - min_size)

# Add COMPANY nodes in sorted order (largest first)
for company in company_ids_sorted:
    x, y = pos[company]
    company_x.append(x)
    company_y.append(y)
    company_text.append(str(company))
    company_color.append('#EF553B')
    
    connections = degree_dict[company]
    # Scale size based on connection count
    scaled_size = scale_size(
        connections, 
        min_company_degree, 
        max_company_degree,
        COMPANY_MIN_SIZE, 
        COMPANY_MAX_SIZE
    )
    company_size.append(scaled_size)
    
    # Custom border for highlighted company
    if highlighted_company and company == highlighted_company:
        company_border_width.append(4)  # Thicker border
        company_border_color.append('#000000')  # Black border
    else:
        company_border_width.append(1)
        company_border_color.append('#000000')
    
    # Hover text
    personas = gr_net_f.filter(pl.col('company_id') == company)['persona_id'].to_list()
    rank = company_ids_sorted.index(company) + 1
    hover_text = f"<b>Company #{rank}:</b> {company}<br>"
    hover_text += f"<b>Personas worked here:</b> {connections}<br>"
    hover_text += f"<b>Connection rank:</b> {rank}/{len(company_ids_sorted)}<br>"
    if connections > 0:
        for persona in personas[:5]:
            persona_name = df_all_personas.filter(pl.col('persona_id')==persona)['full_name'][0].title()
            hover_text += f" • {persona_name}<br>"
        if connections > 5:
            hover_text += f" • ... and {connections - 5} more"
    company_hover.append(hover_text)

# Add PERSONA nodes
for persona in persona_ids:
    x, y = pos[persona]
    persona_x.append(x)
    persona_y.append(y)
    persona_color.append('#636efa')
    
    connections = degree_dict[persona]
    # Scale size based on connection count
    scaled_size = scale_size(
        connections,
        min_persona_degree,
        max_persona_degree,
        PERSONA_MIN_SIZE,
        PERSONA_MAX_SIZE
    )
    persona_size.append(scaled_size)
    
    # Hover text
    companies = gr_net_f.filter(pl.col('persona_id') == persona)['company_id'].to_list()
    persona_name = df_all_personas.filter(pl.col('persona_id')==persona)['full_name'][0].title()
    hover_text = f"<b>Persona:</b> {persona_name}<br>"
    hover_text += f"<b>Companies worked at:</b> {connections}<br>"
    if connections > 0:
        # Check if worked at highlighted company
        if highlighted_company:
            worked_at_highlighted = highlighted_company in companies
            if worked_at_highlighted:
                hover_text += f"<b>Worked at {highlighted_company}:</b> ✓<br>"
        
        hover_text += "<br>".join([f"  • {comp}" for comp in companies[:5]])
        if connections > 5:
            hover_text += f"<br>  • ... and {connections - 5} more"
    persona_hover.append(hover_text)

# Create company node trace
company_trace = go.Scatter(
    x=company_x, y=company_y,
    mode='markers+text',
    hoverinfo='text',
    hovertext=company_hover,
    text=company_text,
    textposition="top center",
    textfont=dict(size=14, color='black'),
    marker=dict(
        color=company_color,
        size=company_size,
        line=dict(
            width=company_border_width,
            color=company_border_color
        ),
        opacity=0.9)
)

# Create persona node trace
persona_trace = go.Scatter(
    x=persona_x, y=persona_y,
    mode='markers',
    hoverinfo='text',
    hovertext=persona_hover,
    text=None,  # No text for personas
    marker=dict(
        color=persona_color,
        size=persona_size,
        line=dict(width=1, color='black'),
        opacity=0.7)
)

# Calculate axis ranges for 1:1 aspect ratio
all_positions = list(pos.values())
x_vals = [p[0] for p in all_positions]
y_vals = [p[1] for p in all_positions]

# Add padding
x_range = [min(x_vals) - 0.5, max(x_vals) + 0.5]
y_range = [min(y_vals) - 0.5, max(y_vals) + 0.5]

# Make axes have the same range for 1:1 aspect
max_range = max(x_range[1] - x_range[0], y_range[1] - y_range[0])
x_center = (x_range[0] + x_range[1]) / 2
y_center = (y_range[0] + y_range[1]) / 2

x_range = [x_center - max_range/2, x_center + max_range/2]
y_range = [y_center - max_range/2, y_center + max_range/2]

# Create figure with 1:1 aspect ratio
fig = go.Figure(data=[edge_trace, persona_trace, company_trace],
                layout=go.Layout(
                    title=f'Persona-Company Network (Companies Ordered by Size)<br><sup>Highlighted: {highlighted_company if highlighted_company else "None"}</sup>',
                    showlegend=False,
                    hovermode='closest',
                    margin=dict(b=20, l=20, r=20, t=100),
                    xaxis=dict(
                        showgrid=False, 
                        zeroline=False, 
                        showticklabels=False,
                        range=x_range,
                        scaleanchor="y",
                        scaleratio=1
                    ),
                    yaxis=dict(
                        showgrid=False, 
                        zeroline=False, 
                        showticklabels=False,
                        range=y_range
                    ),
                    plot_bgcolor='white',
                    paper_bgcolor='white',
                    width=900,
                    height=900
                ))

# Add legend with size examples and highlighting info
# legend_text = f"""
# <b>Node Size = Connection Count</b><br>
# <span style='color:#EF553B'>● Companies</span><br>
# <span style='color:#636efa'>● Personas</span> (hover for details)
# """

# fig.add_annotation(
#     x=0.98, y=0.98,
#     xref="paper", yref="paper",
#     text=legend_text,
#     showarrow=False,
#     font=dict(size=14),
#     align="left",
#     bgcolor="rgba(255, 255, 255, 0.95)",
    
# )

# Add top companies list
top_companies = company_ids_sorted[:10]  # Top 10 companies
top_companies_text = "<b>Top Companies by Connections:</b><br>"
for i, company in enumerate(top_companies, 1):
    connections = degree_dict[company]
    top_connections = degree_dict[top_companies[0]]
    connections_per = f" | {round(connections/top_connections*100)}%" if highlighted_company and company != highlighted_company else ""
    highlight_indicator = " " if highlighted_company and company == highlighted_company else ""
    top_companies_text += f"{dict_company_rev[company]}. {company}: {connections} {connections_per} {highlight_indicator}<br>"

fig.add_annotation(
    x=0.02, y=0.98,
    xref="paper", yref="paper",
    text=top_companies_text,
    showarrow=False,
    font=dict(size=14),
    align="left",
    bgcolor="rgba(255, 255, 255, 0.9)",
    # bordercolor="#666",
    # borderwidth=1
)

# Add probabiliy list

fig.add_annotation(
    x=0.98, y=0.98,
    xref="paper", yref="paper",
    text=annon_prob_text,
    showarrow=False,
    font=dict(
        family="'Courier New', monospace",  # Multiple fallbacks
        size=12,
        color="black"
    ),
    align="left",
    bgcolor="rgba(255, 255, 255, 0.95)",
    
)
fig.write_image((path_output_images/f'network_{current_company_id}.webp'))
fig.show()

Show the code

amount = 5

tmp = df_full_personas_who_worked_in_company.sort(
    ["inferred_salary", "linkedin_connections", "inferred_years_experience"],
    descending=True,
)
tmp_gr = df_full_personas_experiences_plus.group_by('persona_id').agg(pl.len().alias('experience_count'))
tmp = df_full_personas_who_worked_in_company.join(tmp_gr, on='persona_id').sort('experience_count',descending=True)

tmp2 = pl.concat(
    [tmp.filter(pl.col('still_associated')==True, pl.col('higher_up')==True)[:amount*2],
     tmp.filter(pl.col('still_associated')==True, pl.col('higher_up')==False)[:amount*2],
     tmp.filter(pl.col('still_associated')==False, pl.col('higher_up')==True)[:amount*1],
     tmp.filter(pl.col('still_associated')==False, pl.col('higher_up')==False)[:amount*1],
    ]
).sort("full_name")

list_persona_for_plot = tmp2['persona_id'].to_list()

Show the code

# Workforce data

Show the code

def def_plotly_experience_range(current_persona_id):
    tmp_df = (df_full_personas_who_worked_in_company
              .filter(pl.col('persona_id')==current_persona_id)
              .with_columns(pl.col('end_year').fill_null(2021))['start_year','end_year'])
    
    fig_tmp = copy.deepcopy(fig_company_hiring_trend)
    fig_tmp.add_vrect(
        x0=tmp_df[0,'start_year'],
        x1=tmp_df[0,'end_year'],
        fillcolor="blue",
        opacity=0.1,
        line_width=0 
    )
    return fig_tmp

def def_plotly_experience_gantt(current_persona_id):
    px_data = (df_full_personas_experiences_plus
               .filter(pl.col('persona_id')==current_persona_id)
               .with_columns(
                   pl.col('end_date').fill_null(datetime.datetime(2020, 1, 1, 0,0)),
                   pl.col('company_name').str.to_uppercase(),
                   # pl.col('company_name').str.to_uppercase().str.replace_all('&', '-and-')
               )
               .sort('start_date'))
    
    y_order = px_data['company_name'].to_list()
    
    fig = px.timeline(px_data,x_start="start_date", x_end="end_date", y="company_name",
                      color='target',hover_data=["title_name"], height=140+30*len(px_data),
                      category_orders={"company_name": y_order},
                      color_discrete_map={True:'#EF553B',  False:'#636efa'},
                      labels={'target':'Target', 'start_date':'Recruited', 'end_date':'If-Resigned', 
                             'company_name':'Company', 'title_name':'Job role'}
                     # title=f"Experience of {current_persona_name}.",
                     )
    fig.update_yaxes(
        # autorange="reversed",
                              showgrid=True,
                              gridcolor='lightgray',
                              gridwidth=1,
                              griddash='dot'
    )
    fig.update_layout(showlegend=False, xaxis_title=None, yaxis_title=None)
    return fig

4 Workforce sample

4.1 Alessandro Bompadre

Job title: Senior project developer
Socials: https://linkedin.com/in/alessandro-bompadre-76568254

4.1.1 Alessandro Bompadre’s working period at gft group

4.1.2 Gantt plot of Alessandro Bompadre’s experience

4.2 Andrea Aulisi

Job title: Csr, sostenibilitã ambientale e sociale, razionalizzazione dell’energia iso 50001, iso 14001, sa8000
Socials: https://linkedin.com/in/andrea-aulisi-9953854 | https://linkedin.com/in/andreaaulisi | https://twitter.com/listenthinkplay

4.2.1 Andrea Aulisi’s working period at gft group

4.2.2 Gantt plot of Andrea Aulisi’s experience

4.3 Andrew Leslie

Job title: Solution architect
Socials: https://linkedin.com/in/andrew-leslie-4620662 | https://facebook.com/andrewaleslie | https://linkedin.com/in/andrewleslie | https://twitter.com/eilselwerdna

4.3.1 Andrew Leslie’s working period at gft group

4.3.2 Gantt plot of Andrew Leslie’s experience

4.4 Andrés Santos

Job title: Senior front end developer with angular
Socials: https://linkedin.com/in/andr%c3%a9s-gesteira-santos-26a95813 | https://linkedin.com/in/andrã©s-gesteira-santos-26a95813 | https://linkedin.com/in/andrés-gesteira-santos-26a95813

4.4.1 Andrés Santos’s working period at gft group

4.4.2 Gantt plot of Andrés Santos’s experience

4.5 Angel Rey

4.5.1 Angel Rey’s working period at gft group

4.5.2 Gantt plot of Angel Rey’s experience

4.6 Carlos Diez

4.6.1 Carlos Diez’s working period at gft group

4.6.2 Gantt plot of Carlos Diez’s experience

4.7 Carlos Ramallo

Job title: Jefe de proyectos and pmo
Socials: https://linkedin.com/in/carlos-eduardo-ramallo-272aa11b | https://linkedin.com/in/carlosramallo

4.7.1 Carlos Ramallo’s working period at gft group

4.7.2 Gantt plot of Carlos Ramallo’s experience

4.8 Cristiano Nobile

Job title: Executive manager
Socials: https://linkedin.com/in/cristianonobile

4.8.1 Cristiano Nobile’s working period at gft group

4.8.2 Gantt plot of Cristiano Nobile’s experience

4.9 Edgar Rivera

Job title: Gcp customer engineer
Socials: https://plus.google.com/+edgarriverapiedrahita | https://meetup.com/members/14906411 | https://angel.co/edgar-rivera | https://linkedin.com/in/edgar-rivera-mba-pmp-07823b29 | https://linkedin.com/in/edgar-rivera-pmp | https://linkedin.com/in/edgar-rivera-vp-pmp-07823b29 | https://linkedin.com/in/edgarmariorivera | https://facebook.com/edgarmariorivera | https://gravatar.com/edgarmariorivera | https://github.com/edgarmariorivera | https://klout.com/edgarrivera | https://twitter.com/edgarrivera | https://youtube.com/user/mredgarmariorivera

4.9.1 Edgar Rivera’s working period at gft group

4.9.2 Gantt plot of Edgar Rivera’s experience

4.10 Guido Esposito

Job title: Guidewire solution architect
Socials: https://facebook.com/fresco.basilico | https://linkedin.com/in/guido-esposito-299773a0 | https://linkedin.com/in/guidoesposito

4.10.1 Guido Esposito’s working period at gft group

4.10.2 Gantt plot of Guido Esposito’s experience

4.11 Ian Rosen

Job title: Quantitative developer
Socials: https://linkedin.com/in/ian-rosen-0a92542 | https://linkedin.com/in/ianthebear

4.11.1 Ian Rosen’s working period at gft group

4.11.2 Gantt plot of Ian Rosen’s experience

4.12 J.Carlos Damián

Job title: Analista programador de sistemas
Socials: https://linkedin.com/in/j-carlos-damián-81002589

4.12.1 J.Carlos Damián’s working period at gft group

4.12.2 Gantt plot of J.Carlos Damián’s experience

4.13 Lara Morgantini

Job title: Programmatrice abap
Socials: https://linkedin.com/in/lara-morgantini-14391a50

4.13.1 Lara Morgantini’s working period at gft group

4.13.2 Gantt plot of Lara Morgantini’s experience

4.14 Magnus Deuling

Job title: Lead user experience consultant
Socials: https://linkedin.com/in/magnus-a-vh-deuling-ba554aa | https://linkedin.com/in/magnusdeuling | https://github.com/magnusdeuling | https://facebook.com/magnusdeuling | https://twitter.com/magnusdeuling

4.14.1 Magnus Deuling’s working period at gft group

4.14.2 Gantt plot of Magnus Deuling’s experience

4.15 Marcelo Azevedo

Job title: Arquiteto sãªnior
Socials: https://linkedin.com/in/marcelo-azevedo-29a83610 | https://linkedin.com/in/marcelogazevedo | https://twitter.com/mgazevedo | https://stackoverflow.com/users/943430

4.15.1 Marcelo Azevedo’s working period at gft group

4.15.2 Gantt plot of Marcelo Azevedo’s experience

4.16 Marcio Guimaraes

Job title: Database administrator
Socials: https://linkedin.com/in/marcio-guimaraes-ocp-mba-338b6117 | https://linkedin.com/in/marciohg | https://twitter.com/marciohg

4.16.1 Marcio Guimaraes’s working period at gft group

4.16.2 Gantt plot of Marcio Guimaraes’s experience

4.17 Marcos De Souza

Job title: Sap fi co
Socials: https://linkedin.com/in/marcos-joão-de-souza-7b325825 | https://linkedin.com/in/marcos-joã£o-de-souza-7b325825

4.17.1 Marcos De Souza’s working period at gft group

4.17.2 Gantt plot of Marcos De Souza’s experience

4.18 Mario García

Job title: Project manager
Socials: https://linkedin.com/in/mariopm

4.18.1 Mario García’s working period at gft group

4.18.2 Gantt plot of Mario García’s experience

4.19 Mark Grady

Job title: Lead user experience designer
Socials: https://quora.com/mark-grady | https://linkedin.com/in/mark-grady-45359 | https://linkedin.com/in/mrtgrady | https://flickr.com/people/mrtgrady | https://twitter.com/mrtgrady | https://facebook.com/mrtgrady

4.19.1 Mark Grady’s working period at gft group

4.19.2 Gantt plot of Mark Grady’s experience

4.20 Martín De La Cruz

Job title: Business project manager
Socials: https://linkedin.com/in/martindelacruzciia

4.20.1 Martín De La Cruz’s working period at gft group

4.20.2 Gantt plot of Martín De La Cruz’s experience

4.21 Mateusz Tucholski

Job title: Junior java developer
Socials: https://linkedin.com/in/mateusz-tucholski-ba31b0aa | https://github.com/mtucholski.

4.21.1 Mateusz Tucholski’s working period at gft group

4.21.2 Gantt plot of Mateusz Tucholski’s experience

4.22 Maurício Messias

Job title: Agile coach
Socials: https://linkedin.com/in/maurício-messias-4425a05 | https://linkedin.com/in/mmessias

4.22.1 Maurício Messias’s working period at gft group

4.22.2 Gantt plot of Maurício Messias’s experience

4.23 Neal Leavitt

Job title: Vp-retail
Socials: https://linkedin.com/in/neal-leavitt-4a563411 | https://linkedin.com/in/neal-leavitt-9267a95

4.23.1 Neal Leavitt’s working period at gft group

4.23.2 Gantt plot of Neal Leavitt’s experience

4.24 Pat Bitton

Job title: Contract writer and editor
Socials: https://facebook.com/pat.bitton | https://linkedin.com/in/patbitton | https://twitter.com/patbitton

4.24.1 Pat Bitton’s working period at gft group

4.24.2 Gantt plot of Pat Bitton’s experience

4.25 Peter Nguyen

Job title: Director of marketing
Socials: https://facebook.com/pete.nguyen.14 | https://linkedin.com/in/peter-nguyen-56169828

4.25.1 Peter Nguyen’s working period at gft group

4.25.2 Gantt plot of Peter Nguyen’s experience

4.26 Rafał Broll

Job title: .net technical lead
Socials: https://github.com/rafalbroll | https://linkedin.com/in/rafalbroll | https://facebook.com/rafalbroll

4.26.1 Rafał Broll’s working period at gft group

4.26.2 Gantt plot of Rafał Broll’s experience

4.27 Roberto Ito

Job title: Delivery manager
Socials: https://linkedin.com/in/roberto-ito-470b8b13 | https://linkedin.com/in/robertoito

4.27.1 Roberto Ito’s working period at gft group

4.27.2 Gantt plot of Roberto Ito’s experience

4.28 Santiago De La Hoz Ortega

Job title: Lead project manager
Socials: https://linkedin.com/in/santiago-de-la-hoz-ortega-b90340a0

4.28.1 Santiago De La Hoz Ortega’s working period at gft group

4.28.2 Gantt plot of Santiago De La Hoz Ortega’s experience

4.29 Tremain Waterson

Job title: User interface and user experience design lead
Socials: https://linkedin.com/in/tremain-waterson-ba723a11 | https://linkedin.com/in/wemustcreate

4.29.1 Tremain Waterson’s working period at gft group

4.29.2 Gantt plot of Tremain Waterson’s experience

4.30 Wiliam Faria

Job title: Data protection officer
Socials: https://linkedin.com/in/wiliam-faria-a548b717 | https://facebook.com/wiliam.faria.1

4.30.1 Wiliam Faria’s working period at gft group

4.30.2 Gantt plot of Wiliam Faria’s experience

Show the code

df_full_personas_who_worked_in_company.write_parquet(current_company_parquet)